Research Engineer

Responsibilities

• Convert research prototypes into production-grade software for reliable, real-time execution on hardware.
• Harden perception pipelines involving pose estimation, SLAM, and calibration for embedded platforms.
• Profile and optimize CPU, memory, and GPU performance using profiling tools and microbenchmarks.
• Write, profile, and debug CUDA kernels for compute-intensive workloads.
• Integrate research outputs into production code with testing, error handling, and observability.
• Containerize and package workloads with Docker for infrastructure-team deployment and scaling.
• Work with researchers to balance algorithmic accuracy, latency, and resource usage.
• Coordinate with infrastructure teams to hand off production-ready workloads using orchestration and compute systems.

Requirements

• 3+ years of industry software engineering experience focused on systems, performance, or production ML.
• Strong proficiency in C++, including modern C++17/20, memory management, and performance-conscious coding.
• Experience writing, profiling, and debugging CUDA GPU kernels.
• Experience optimizing CPU performance, including profiling, cache behavior, SIMD, and latency reduction.
• Proficiency in Python and familiarity with PyTorch and TensorFlow sufficient to read and modify research code.
• Comfort with Linux systems, build systems, debugging tools, and containerization.
• Experience shipping research or prototype code in production is valued.
• Experience with real-time or embedded systems, perception, computer vision, or robotics is valued.
• Experience optimizing model inference with TensorRT, ONNX Runtime, or similar tools is valued.
• Understanding of the lifecycle from research notebook to containerized, monitored production service is valued.